Hugging Face's logo
Concedo's picture
37 13

Concedo

concedo
Lycan22's profile picture maldv's profile picture 21world's profile picture
·

AI & ML interests

Hi, I'm Concedo, also known as LostRuins. I'm the dev of KoboldCpp.

Organizations

Caldera AI's profile picture KoboldAI's profile picture Modron AI's profile picture Koboldcpp's profile picture BeaverAI's profile picture

concedo's activity

New activity in Gryphe/ChatGPT-4o-Writing-Prompts 6 days ago

Slight corruption in dataset

1
#1 opened 6 days ago by concedo
New activity in DontPlanToEnd/UGI-Leaderboard 3 months ago

Eval request - mini magnum unboxed
#23 opened 3 months ago by concedo
New activity in concedo/Mini-Magnum-Unboxed-12B 3 months ago

Is there a plan for a magnum V2 version of this model?

4
#1 opened 3 months ago by SaisExperiments
New activity in concedo/Mini-Magnum-Unboxed-12B-GGUF 3 months ago

Upload folder using huggingface_hub

2
#1 opened 3 months ago by concedo
New activity in concedo/Mini-Magnum-Unboxed-12B 3 months ago

Upload folder using huggingface_hub

2
#3 opened 3 months ago by concedo

[WIP] Upload folder using huggingface_hub (multi-commit ac840cbd2fa2506a8672ed415d6d4f8913465bff5e1a3567c66ab06c6974e87f)
#2 opened 3 months ago by concedo
New activity in concedo/KobbleSmall-2B 3 months ago

Kobo

3
#1 opened 3 months ago by TheDrummer
New activity in koboldcpp/kcppbins 4 months ago

[bug] KoboldCpp 1.71.1 wrong detection of quants not only llama type and cause quality loss

2
#1 opened 4 months ago by SFBAI
New activity in TheDrummer/Tiger-Gemma-9B-v1 4 months ago

The tiger models tend to go crazy on LM Studio ?

8
#4 opened 4 months ago by Dihelson
New activity in bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF 4 months ago

K quants should not contain IQ4_NL types inside

4
#4 opened 4 months ago by concedo
New activity in concedo/WebTokenizer 6 months ago

Add more models

1
#1 opened 6 months ago by xzuyn
New activity in TheDrummer/Moistral-11B-v3 6 months ago

🏆.Best NSFW 11B model ever made.💦💦💦💦

3
#4 opened 6 months ago by Ransss
New activity in Orenguteng/Llama-3-8B-Lexi-Uncensored 7 months ago

Re-quant?

5
#5 opened 7 months ago by BlueNipples
New activity in hjhj3168/Llama-3-8b-Orthogonalized-exl2 7 months ago

🚩 Report: Legal issue(s)

40
#2 opened 7 months ago by chrisjcundy
New activity in Orenguteng/Llama-3-8B-Lexi-Uncensored-GGUF 7 months ago

Reconverted and requantized with latest GGUF to fix llama3 tokenizer

10
#5 opened 7 months ago by concedo
New activity in mradermacher/Llama-3-SnowyRP-8B-V1-B-GGUF 7 months ago

May need reconversion

1
#1 opened 7 months ago by concedo
New activity in concedo/KobbleTinyV2-1.1B 7 months ago

Upload 7 files

1
#1 opened 7 months ago by concedo
New activity in Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1-GGUF 7 months ago

May require reconversion due to llama.cpp enhancements

8
#1 opened 7 months ago by concedo
New activity in saucam/llama-airo-3 7 months ago

Training Mistake, model is ruined.

4
#1 opened 7 months ago by concedo
New activity in koboldcpp/mmproj 7 months ago

LLaMa-3-8B mmproj?

4
#2 opened 7 months ago by Joseph717171